StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction

Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature extraction or multi-stage automatic speech recognition (ASR) and text-to-speech (TTS) pipelines, which separate transcription from audio reconstruction and often amplify distortions. This work introduces StutterZero and StutterFormer, the first end-to-end waveform-to-waveform models that directly convert stuttered speech into fluent speech while jointly predicting its transcription. StutterZero employs a convolutional-bidirectional LSTM encoder-decoder with attention, whereas StutterFormer integrates a dual-stream Transformer with shared acoustic-linguistic representations. Both architectures are trained on paired stuttered-fluent data synthesized from the SEP-28K and LibriStutter corpora and evaluated on unseen speakers from the FluencyBank dataset. Across all benchmarks, StutterZero had a 24% decrease in Word Error Rate (WER) and a 31% improvement in semantic similarity (BERTScore) compared to the leading Whisper-Medium model. StutterFormer achieved better results, with a 28% decrease in WER and a 34% improvement in BERTScore. The results validate the feasibility of direct end-to-end stutter-to-fluent speech conversion, offering new opportunities for inclusive human-computer interaction, speech therapy, and accessibility-oriented AI systems.

Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking

Pre-trained transformer-based models have significantly advanced automatic speech recognition (ASR), yet they remain sensitive to accent and dialectal variations, resulting in elevated word error rates (WER) in linguistically diverse languages such as English and Persian. To address this challenge, we propose an accent-invariant ASR framework that integrates accent and dialect classification into the recognition pipeline. Our approach involves training a spectrogram-based classifier to capture accent-specific cues, masking the regions most influential to its predictions, and using the masked spectrograms for data augmentation. This enhances the robustness of ASR models against accent variability. We evaluate the method using both English and Persian speech. For Persian, we introduce a newly collected dataset spanning multiple regional accents, establishing the first systematic benchmark for accent variation in Persian ASR that fills a critical gap in multilingual speech research and provides a foundation for future studies on low-resource, linguistically diverse languages. Experimental results with the Whisper model demonstrate that our masking and augmentation strategy yields substantial WER reductions in both English and Persian settings, confirming the effectiveness of the approach. This research advances the development of multilingual ASR systems that are resilient to accent and dialect diversity. Code and dataset are publicly available at: https://github.com/MH-Sameti/Accent_invariant_ASR

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition

Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical workaround, it often introduces systematic, accent-specific errors that filtering fails to fix. We ask: How can we correct these recurring biases without target ground truth? We propose a simple parameter-space correction: in a source domain containing both real and pseudo-labeled data, two ASR models are fine-tuned from the same initialization, one on ground-truth labels and the other on pseudo-labels, and their weight difference forms a correction vector that captures pseudo-label biases. When applied to a pseudo-labeled target model, this vector enhances recognition, achieving up to a 35% relative Word Error Rate (WER) reduction on AfriSpeech-200 across ten African accents with the Whisper tiny model.

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Despite rapid progress, ASR evaluation remains saturated with short-form English, and efficiency is rarely reported. We present the Open ASR Leaderboard, a fully reproducible benchmark and interactive leaderboard comparing 60+ open-source and proprietary systems across 11 datasets, including dedicated multilingual and long-form tracks. We standardize text normalization and report both word error rate (WER) and inverse real-time factor (RTFx), enabling fair accuracy-efficiency comparisons. For English transcription, Conformer encoders paired with LLM decoders achieve the best average WER but are slower, while CTC and TDT decoders deliver much better RTFx, making them attractive for long-form and offline use. Whisper-derived encoders fine-tuned for English improve accuracy but often trade off multilingual coverage. All code and dataset loaders are open-sourced to support transparent, extensible evaluation.

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models

Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper proposes a framework to design fine-tuned variants of Whisper which address the above problem. Structured sparsity is enforced via the Sparse Group LASSO penalty as a loss regularizer, to reduce the number of FLOating Point operations (FLOPs). Further, a weight statistics aware pruning algorithm is proposed. We also design our custom text normalizer for WER evaluation. On Common Voice 11.0 Hindi dataset, we obtain, without degrading WER, (a) 35.4% reduction in model parameters, 14.25% lower memory consumption and 18.5% fewer FLOPs on Whisper-small, and (b) 31% reduction in model parameters, 15.29% lower memory consumption and 16.95% fewer FLOPs on Whisper-medium; and, (c) substantially outperform the state-of-the-art Iterative Magnitude Pruning based method by pruning 18.7% more parameters along with a 12.31 reduction in WER.

Machine Unlearning in Speech Emotion Recognition via Forget Set Alone

Speech emotion recognition aims to identify emotional states from speech signals and has been widely applied in human-computer interaction, education, healthcare, and many other fields. However, since speech data contain rich sensitive information, partial data can be required to be deleted by speakers due to privacy concerns. Current machine unlearning approaches largely depend on data beyond the samples to be forgotten. However, this reliance poses challenges when data redistribution is restricted and demands substantial computational resources in the context of big data. We propose a novel adversarial-attack-based approach that fine-tunes a pre-trained speech emotion recognition model using only the data to be forgotten. The experimental results demonstrate that the proposed approach can effectively remove the knowledge of the data to be forgotten from the model, while preserving high model performance on the test set for emotion recognition.

UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these tasks separately rather than through a unified framework. This work aims to integrate these two tasks into one unified model. Although discrete speech tokenization enables joint modeling, its inherent information loss limits performance in both recognition and generation. In this work, we present UniVoice, a unified LLM framework through continuous representations that seamlessly integrates speech recognition and synthesis within a single model. Our approach combines the strengths of autoregressive modeling for speech recognition with flow matching for high-quality generation. To mitigate the inherent divergence between autoregressive and flow-matching models, we further design a dual attention mechanism, which switches between a causal mask for recognition and a bidirectional attention mask for synthesis. Furthermore, the proposed text-prefix-conditioned speech infilling method enables high-fidelity zero-shot voice cloning. Experimental results demonstrate that our method can achieve or exceed current single-task modeling methods in both ASR and zero-shot TTS tasks. This work explores new possibilities for end-to-end speech understanding and generation.

EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Speech Language Models (SLMs) have made significant progress in spoken language understanding. Yet it remains unclear whether they can fully perceive non lexical vocal cues alongside spoken words, and respond with empathy that aligns with both emotional and contextual factors. Existing benchmarks typically evaluate linguistic, acoustic, reasoning, or dialogue abilities in isolation, overlooking the integration of these skills that is crucial for human-like, emotionally intelligent conversation. We present EchoMind, the first interrelated, multi-level benchmark that simulates the cognitive process of empathetic dialogue through sequential, context-linked tasks: spoken-content understanding, vocal-cue perception, integrated reasoning, and response generation. All tasks share identical and semantically neutral scripts that are free of explicit emotional or contextual cues, and controlled variations in vocal style are used to test the effect of delivery independent of the transcript. EchoMind is grounded in an empathy-oriented framework spanning 3 coarse and 12 fine-grained dimensions, encompassing 39 vocal attributes, and evaluated using both objective and subjective metrics. Testing 12 advanced SLMs reveals that even state-of-the-art models struggle with high-expressive vocal cues, limiting empathetic response quality. Analyses of prompt strength, speech source, and ideal vocal cue recognition reveal persistent weaknesses in instruction-following, resilience to natural speech variability, and effective use of vocal cues for empathy. These results underscore the need for SLMs that integrate linguistic content with diverse vocal cues to achieve truly empathetic conversational ability.

MedVoiceBias: A Controlled Study of Audio LLM Behavior in Clinical Decision-Making

As large language models transition from text-based interfaces to audio interactions in clinical settings, they might introduce new vulnerabilities through paralinguistic cues in audio. We evaluated these models on 170 clinical cases, each synthesized into speech from 36 distinct voice profiles spanning variations in age, gender, and emotion. Our findings reveal a severe modality bias: surgical recommendations for audio inputs varied by as much as 35% compared to identical text-based inputs, with one model providing 80% fewer recommendations. Further analysis uncovered age disparities of up to 12% between young and elderly voices, which persisted in most models despite chain-of-thought prompting. While explicit reasoning successfully eliminated gender bias, the impact of emotion was not detected due to poor recognition performance. These results demonstrate that audio LLMs are susceptible to making clinical decisions based on a patient's voice characteristics rather than medical evidence, a flaw that risks perpetuating healthcare disparities. We conclude that bias-aware architectures are essential and urgently needed before the clinical deployment of these models.

Enhancing Speech Emotion Recognition via Fine-Tuning Pre-Trained Models and Hyper-Parameter Optimisation

We propose a workflow for speech emotion recognition (SER) that combines pre-trained representations with automated hyperparameter optimisation (HPO). Using SpeechBrain wav2vec2-base model fine-tuned on IEMOCAP as the encoder, we compare two HPO strategies, Gaussian Process Bayesian Optimisation (GP-BO) and Tree-structured Parzen Estimators (TPE), under an identical four-dimensional search space and 15-trial budget, with balanced class accuracy (BCA) on the German EmoDB corpus as the objective. All experiments run on 8 CPU cores with 32 GB RAM. GP-BO achieves 0.96 BCA in 11 minutes, and TPE (Hyperopt implementation) attains 0.97 in 15 minutes. In contrast, grid search requires 143 trials and 1,680 minutes to exceed 0.9 BCA, and the best AutoSpeech 2020 baseline reports only 0.85 in 30 minutes on GPU. For cross-lingual generalisation, an EmoDB-trained HPO-tuned model improves zero-shot accuracy by 0.25 on CREMA-D and 0.26 on RAVDESS. Results show that efficient HPO with pre-trained encoders delivers competitive SER on commodity CPUs. Source code to this work is available at: https://github.com/youngaryan/speechbrain-emotion-hpo.